@inproceedings{saha-nanda-2023-banglanlp-blp,
title = "{B}angla{NLP} at {BLP}-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of {B}angla Social Media Posts",
author = "Saha, Saumajit and
Nanda, Albert",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Sadeque, Farig and
Amin, Ruhul",
booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.banglalp-1.34",
doi = "10.18653/v1/2023.banglalp-1.34",
pages = "266--272",
abstract = "Bangla is the 7th most widely spoken language globally, with a staggering 234 million native speakers primarily hailing from India and Bangladesh. This morphologically rich language boasts a rich literary tradition, encompassing diverse dialects and language-specific challenges. Despite its linguistic richness and history, Bangla remains categorized as a low-resource language within the natural language processing (NLP) and speech community. This paper presents our submission to Task 2 (Sentiment Analysis of Bangla Social Media Posts) of the BLP Workshop. We experimented with various Transformer-based architectures to solve this task. Our quantitative results show that transfer learning really helps in better learning of the models in this low-resource language scenario. This becomes evident when we further finetuned a model that had already been finetuned on Twitter data for sentiment analysis task and that finetuned model performed the best among all other models. We also performed a detailed error analysis where we found some instances where ground truth labels need to be looked at. We obtained a micro-F1 of 67.02{\%} on the test set and our performance in this shared task is ranked at 21 in the leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-nanda-2023-banglanlp-blp">
<titleInfo>
<title>BanglaNLP at BLP-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of Bangla Social Media Posts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saumajit</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Nanda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farig</namePart>
<namePart type="family">Sadeque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bangla is the 7th most widely spoken language globally, with a staggering 234 million native speakers primarily hailing from India and Bangladesh. This morphologically rich language boasts a rich literary tradition, encompassing diverse dialects and language-specific challenges. Despite its linguistic richness and history, Bangla remains categorized as a low-resource language within the natural language processing (NLP) and speech community. This paper presents our submission to Task 2 (Sentiment Analysis of Bangla Social Media Posts) of the BLP Workshop. We experimented with various Transformer-based architectures to solve this task. Our quantitative results show that transfer learning really helps in better learning of the models in this low-resource language scenario. This becomes evident when we further finetuned a model that had already been finetuned on Twitter data for sentiment analysis task and that finetuned model performed the best among all other models. We also performed a detailed error analysis where we found some instances where ground truth labels need to be looked at. We obtained a micro-F1 of 67.02% on the test set and our performance in this shared task is ranked at 21 in the leaderboard.</abstract>
<identifier type="citekey">saha-nanda-2023-banglanlp-blp</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.34</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.34</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>266</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanglaNLP at BLP-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of Bangla Social Media Posts
%A Saha, Saumajit
%A Nanda, Albert
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Sadeque, Farig
%Y Amin, Ruhul
%S Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F saha-nanda-2023-banglanlp-blp
%X Bangla is the 7th most widely spoken language globally, with a staggering 234 million native speakers primarily hailing from India and Bangladesh. This morphologically rich language boasts a rich literary tradition, encompassing diverse dialects and language-specific challenges. Despite its linguistic richness and history, Bangla remains categorized as a low-resource language within the natural language processing (NLP) and speech community. This paper presents our submission to Task 2 (Sentiment Analysis of Bangla Social Media Posts) of the BLP Workshop. We experimented with various Transformer-based architectures to solve this task. Our quantitative results show that transfer learning really helps in better learning of the models in this low-resource language scenario. This becomes evident when we further finetuned a model that had already been finetuned on Twitter data for sentiment analysis task and that finetuned model performed the best among all other models. We also performed a detailed error analysis where we found some instances where ground truth labels need to be looked at. We obtained a micro-F1 of 67.02% on the test set and our performance in this shared task is ranked at 21 in the leaderboard.
%R 10.18653/v1/2023.banglalp-1.34
%U https://aclanthology.org/2023.banglalp-1.34
%U https://doi.org/10.18653/v1/2023.banglalp-1.34
%P 266-272
Markdown (Informal)
[BanglaNLP at BLP-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of Bangla Social Media Posts](https://aclanthology.org/2023.banglalp-1.34) (Saha & Nanda, BanglaLP 2023)
ACL